EP2926318B1 - Image processing device and method - Google Patents

Image processing device and method Download PDF

Info

Publication number
EP2926318B1
EP2926318B1 EP13811010.1A EP13811010A EP2926318B1 EP 2926318 B1 EP2926318 B1 EP 2926318B1 EP 13811010 A EP13811010 A EP 13811010A EP 2926318 B1 EP2926318 B1 EP 2926318B1
Authority
EP
European Patent Office
Prior art keywords
interest
line model
line
image
model
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
EP13811010.1A
Other languages
German (de)
English (en)
French (fr)
Other versions
EP2926318A1 (en
Inventor
Rafael Wiemker
Tobias Klinder
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Philips GmbH
Koninklijke Philips NV
Original Assignee
Philips GmbH
Koninklijke Philips NV
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Philips GmbH, Koninklijke Philips NV filed Critical Philips GmbH
Publication of EP2926318A1 publication Critical patent/EP2926318A1/en
Application granted granted Critical
Publication of EP2926318B1 publication Critical patent/EP2926318B1/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/12—Edge-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2200/00—Indexing scheme for image data processing or generation, in general
    • G06T2200/04—Indexing scheme for image data processing or generation, in general involving 3D image data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10072—Tomographic images
    • G06T2207/10081—Computed x-ray tomography [CT]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20004—Adaptive image processing
    • G06T2207/20012—Locally adaptive
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20016—Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20212—Image combination
    • G06T2207/20221—Image fusion; Image merging
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30061—Lung

Definitions

  • the present invention relates to an image processing device and a corresponding image processing method for detecting line structures in an image data set.
  • the present invention particularly relates to the processing of medical images, such as x-ray images, for instance to find lobar fissures between the lung lobes.
  • Lobar fissures are thin boundaries that divide the lungs into five lobes; the left lung consists of two lobes and the right lung consists of three lobes.
  • CT Computed Tomography
  • automatic segmentation of lung lobes from CT data is becoming clinically relevant as an enabler for, e.g., lobe-based quantitative analysis for diagnostics or more accurate interventional planning.
  • Attenuation of the fissures in CT scans is typically greater than the surrounding lung parenchyma, so that fissures appear as bright plate-like structures.
  • segmentation of the lung lobes is still very challenging especially as the fissures are very thin and thus result in bright lines of only one or two pixel thickness in a cross-sectional view even on latest high resolution CT. For that reason, image noise, partial volume effect, but also different reconstruction kernels and imaging protocols heavily impede the extraction. Finally, lobe segmentation is further complicated once anatomical anomalies are present.
  • Another often used approach is to analyze the eigenvectors of the Hessian matrix of each voxel to measure if a voxel belongs to a locally plate-like object with bright appearance. From a rich set of features, the ones that are best suited for fissure detection are selected in a supervised learning step.
  • fissure detection has been addressed by using different approaches, there are still several limitations.
  • the filter can give low responses for fissure voxels due to the challenges stated above.
  • human observers can in most cases still clearly see the fissures even when the filter is not responding well.
  • the line to be detected is non-continuous (interrupted, consisting of single points); the line consists of line pieces, which may be slightly curved and are not collinear throughout the image (as assumed e.g. for a Hough-transform); the image is very noisy; or the line is fainter in contrast and intensity than the surrounding image structures.
  • Shinhsuke Saita et.al disclose, in 'An extraction algorithm of pulmonary fissures from multislice CT image', Proceedings of SPIE, vol. 5370, 2004, p. 1590-1597 , detecting pulmonary fissures in a CT image data set by providing a 3D (cubic) model, calculating (summing over the voxels) and then extracting the pulmonary fissures.
  • Subhasis Chauduri et.al disclose, in Detection of blood vessels in retinal images using two-dimensional matched filters', IEEE Transactions On Medical Images, IEEE Service Center, Piscataway, NJ, US, vol. 23, no. 10, 2004, p. 1196-1204 , a detection algorithm for detecting blood vessels in retinal images in which a matched filter detection is used to detect piecewise linear segments of blood vessels.
  • a computer program which comprises program code means for causing a computer to perform the steps of the processing method when said computer program is carried out on a computer.
  • a detection algorithm which may also be regarded as a filter, is effectively applied that enhances the line structures to be detected (e.g. the fissures in a data set of a human lung) by measuring if a voxel belongs locally to (thin) line segments of bright appearance, e.g. in a cross-sectional view of an available 3D image data set.
  • This new line enhancing filter tests multiple hypotheses for each voxel to capture possible line orientations and thus responds well even for faint line structures while giving low response for other objects.
  • the present invention can advantageously be applied for the delineation of the lobar fissures between the five lung lobes, lobar fissures in the liver, guide wires, biopsy needles, vessels, and bronchi in medical images, such as x-ray images obtained by an x-ray device or a CT scanner.
  • said calculation unit is configured to calculate, per voxel of interest of said image data set, several correlation values of a linear correlation between said line model and an image area around said voxel of interest.
  • a linear correlation can be calculated with limited efforts and is very robust against image noise as well as anatomical noise (unrelated closely adjacent structures).
  • said calculation unit is configured to calculate, per voxel of interest of said image data set, several correlation values of said linear correlation between said line model and an image area around said voxel of interest by calculating the ratio of the covariance of intensity values of said image area and said line model over the variance of the intensity values of said image area and the variance of the intensity values of said line model.
  • the proposed line structure detection can be used to detect a line structure in a 3D image data set or in one or more 2D image data sets, e.g. image slices through a 3D image.
  • said model definition unit is configured to define a two-dimensional rectangular line model having a predetermined length and width and wherein said calculation unit is configured to calculate, per pixel of interest of two-dimensional image data set, several correlation values of a correlation between said two-dimensional rectangular line model and a two-dimensional image area around said pixel of interest.
  • a rectangular line model is particularly useful if the image data are available on an rectangular grid resulting in a limited amount and complexity of the required calculations.
  • the length and width can be selected and/or adjusted, e.g. according to the corresponding dimension of the line structure to be detected.
  • said model definition unit is preferably configured to define a two-dimensional rectangular line model having a larger extension in a direction along the line structure to be detected than in a direction perpendicular to the line structure to be detected. This provides that more signal is obtained along the line direction while not considering a large neighbourhood around the line.
  • said calculation unit and said determining unit are configured to repeat the steps of calculating and determining for different two-dimensional image data sets, in particular different image slices of a three-dimensional image data set.
  • a line structure can be detected in a complete 3D image data set, whereby the detection method (particularly the steps of calculating the correlation values and determining the maximum correlation value) is generally carried out per 2D image slices.
  • said model definition unit is configured to define a three-dimensional cuboidal line model having a predetermined length, width and height.
  • the detection method can be applied to a 3D image data set (without applying it separately to image slices).
  • said model definition unit is configured to define a map of voxels or an analytical function as line model.
  • the analytical function is preferably used if a specific appearance (voxel map) is not yet known, and exchanged for a voxel map in a later iteration as will be explained below.
  • said model definition unit is configured to initially define a general line model of the line structure to be detected and to use the maximum correlation values and the corresponding optimal orientations obtained by use of said general line model to define a refined line model of the line structure to be detected, and wherein said calculation unit and said determining unit are configured to repeat the steps of calculating and determining by use of said refined line model.
  • said calculation unit is configured to calculate said correlation values only for voxels belonging to a predetermined region of interest and to determine if a voxel belongs to said predetermined region of interest based on a mask image indicating if a voxel belongs to said predetermined region of interest or a probability value of the probability that a voxel belongs to said predetermined region of interest.
  • Said mask image can, for instance, be obtained from an image segmentation algorithm that e.g. segments a medical image to obtain an indication of organs or desired structures shown in the image. Such segmentation algorithms are widely known in the art. Improved methods also deliver a probability value that a voxel belongs to a predetermined region, e.g. an organ. The use of such a mask image reduces the amount of necessary calculations and further improves the accuracy of the detection of the line structure.
  • said calculation unit is configured to calculate, per voxel of interest of said image data set, several correlation values of a correlation between said line model and an image area around said voxel of interest for different relative orientations of said line model with respect to said image area by rotating said line model and/or said image area around said voxel of interest to change the relative orientation. In this way the change of the orientation is easily obtained.
  • the image processing device further comprises a post-processing unit for identifying within the image data set areas of voxels for which substantially the same optimal orientation has been found.
  • the degree to which the optimal orientation of all voxels in a certain neighborhood agrees is computed and called the local orientedness, i.e. the orientation is an angle, the orientedness is a degree of agreement.
  • said post-processing unit is configured to determine, per voxel of interest, a local orientedness value and to multiply, per voxel of interest, said local orientedness value with the obtained maximum correlation value to obtain an amplified maximum correlation value. In that way, correlations are emphasized if the orientation angles in a certain neighborhood substantially agree.
  • Fig. 1 shows a schematic diagram of an image processing device 10 according to the present invention. It comprises a model definition unit 12 for defining a line model of a line structure to be detected, said line model comprising a number of voxels. Further, a calculation unit 14 is provided for calculating, per voxel of interest of said image data set, several correlation values of a correlation between said line model and an image area around said voxel of interest, said image area comprising a corresponding number of voxels as said line model, wherein for each of a number of different relative orientations of said line model with respect to said image area a respective correlation value is calculated. Still further, a determining unit 16 is provided for determining, per voxel of interest, the maximum correlation value from said calculated correlation values and the corresponding optimal orientation at which said maximum correlation value is obtained.
  • a post-processing unit 18 is provided for identifying within the image data set areas of voxels for which substantially the same optimal orientation has been found, to determine, per voxel of interest, a local orientedness value and to multiply, per voxel of interest, said local orientedness value with the obtained maximum correlation value to obtain an amplified maximum correlation value.
  • the obtained maximum correlation values can, for instance, be used to indicate the detected local structures in the original image data, e.g. in a 2D image, by replacing the original pixel value with the obtained maximum correlation value.
  • a new image can be constructed by using as pixel (or voxel) values the obtained orientedness values, or the product of maximum correlation and local orientedness.
  • the obtained orientation of the max. correlation value is generally not displayed; the orientation angle is mainly needed to construct the orientedness and can then be discarded.
  • the filter is to calculate for each voxel a line measure by correlating a model template of the line structure with the observed image data. Because of the large search space for a potential surface orientation in 3D, the proposed method is preferably applied to lines in 2D, i.e. it is desired to highlight the (generally thin) bright lines structures on cross-sectional images (preferably sagittal and coronal slice images) while suppressing other structures.
  • the present invention preferably provides a detection algorithm (also called filter) which preferably operates on 2D image slices and can be used as an input for further image processing such as 3D-model-based segmentation, 3D-region growing, etc.
  • a detection algorithm also called filter
  • 3D-model-based segmentation 3D-region growing, etc.
  • the filter provides a filter response yielding a goodness value (the maximum correlation value) and an estimated orientation for each image pixel.
  • Fig. 2A shows as an example for an original input image a sagittal CT slice image after lung segmentation, showing pulmonary vessels and horizontal and vertical lobar fissure lines.
  • Fig. 2B shows the filter response as goodness for each pixel (not shown is the filter response as estimated orientation for each pixel).
  • the proposed image processing device 10 assumes a certain model for the line and its neighbourhood.
  • the model is generally not required to be quadratic.
  • a rectangular model is used having independent length / and width w (for instance, of a size of at least 10 x 5 pixels).
  • the model can be an image (e.g. a pixelmap) or an analytical function.
  • the model function is separable in the principal direction e w and e L (e.g. x and y directions).
  • an optional mask image M ( x ) is provided which gives the probability for each pixel that this pixel at location x is part of a region of interest, for instance an organ of interest (e.g. a lung) which information is e.g. derived from a segmentation of the original image.
  • the mask image M ( x ) indicates if or if not a pixel belongs to the region of interest, e.g. by assigning a binary indication value (e.g. 0 or 1) to each pixel.
  • the (preferably linear) correlation of the model with the image pixels x' in an area of extent l ⁇ w centered around x is computed.
  • the linear correlation coefficient is preferably computed as the ratio of the covariance of image and model intensity values over the variance of image and model intensities itself.
  • the correlation is computed by using a weight factor for each pixel x', which is given by the product of the organ likelihood image M( x ) and a bivariate Gaussian function G( x'-x ) which peaks at the center of the model and vanishes towards the model boundaries.
  • ⁇ 2 IM (x) ⁇ (I(x')-I mean ) ⁇ (M(x')-M mean ) ⁇ G(x'-x) ⁇ M(x')/ ⁇ G(x'-x) ⁇ M(x')
  • x' is summed up by the summation ⁇ over all pixel locations x' in the (rectangular) neighborhood mask around x
  • I mean and M mean are the mean values in the neighborhood.
  • the formulas for ⁇ 2 II and ⁇ 2 MM can be obtained by substitution of I and M, respectively.
  • the correlation is preferably computed for each of A orientations (angles; for instance for an angular range of 180°, wherein the angle is increased by 1° for each new computation). Then the highest of all A correlation values and its corresponding orientation angle ⁇ are adopted as the filter output.
  • the iteration over all directions (angles) can be done by rotation of the model into A different directions. However, if the model is separable into two principal directions, then it is computationally more efficient to rotate the image itself rather than the model.
  • FIG. 3 An example of a fissure line model is shown in Fig. 3 .
  • the model patch is defined by its length l in direction of the axis e L and its width w in direction of the axis e W .
  • the orientation of the line is in e L direction.
  • the line profile p ( x W ) along the e W axis is given as the difference of two Gaussians with ⁇ F for the fissure width and ⁇ B for the dark background gap accompanying the fissure.
  • the detection of fissure line pieces which can be of different orientations in the data set is done by multiple hypotheses testing. For each voxel, the correlation of the model in different orientations with the corresponding image data is calculated. The hypothesis that gives the maximum correlation then belongs to the correct orientation of the line piece. To make the calculation of the correlation for a number of angles computationally efficient, the 2D image slice is rotated rather than rotating the model. In that way the necessary convolutions can be carried out for all slice pixels in an axis-parallel and thus separable fashion.
  • the proposed line enhancing filter i.e. the proposed method
  • the proposed line enhancing filter allows defining the local neighbourhood to be evaluated via the length l and the width w of the model.
  • a larger neighbourhood around each voxel when calculating the linear correlation can be considered.
  • a rectangular line model can be defined that has a larger extension in direction of the line with a smaller extent perpendicular to the line.
  • the output of the proposed method can be used to indicate in an original image, e.g. an original sagittal CT slice image as shown in Fig. 4A , the detected line structures (indicated in Fig. 4B a 20, 21, 22, 23, 24, 25) and, if of interest, the width of the filter model indicated by 30 as an example in Fig. 4B around line structure 20.
  • an original image e.g. an original sagittal CT slice image as shown in Fig. 4A
  • the detected line structures indicated in Fig. 4B a 20, 21, 22, 23, 24, 25
  • the width of the filter model indicated by 30 as an example in Fig. 4B around line structure 20.
  • the present invention uses a correlation which generally is the ratio of covariance over the two individual variances, thus requiring three independent convolutions. It is the correlation (rather than simple convolution) which is essential for the capability of the suggested algorithm to detect lines which are much fainter in contrast than the surrounding image structures.
  • FIG. 5A shows an original input image slice of a human lung.
  • Fig. 5B shows an image in which the obtained maximum correlation values of the detected line structures.
  • all neighboring orientation angles ⁇ and correlation values c around a pixel are sampled within a spherical neighborhood with a certain radius, weighted with a radial Gaussian weight function w.
  • this result image is used again as an input image for the same filter procedure as before. This can be repeated in an iterative process.
  • the eigenvalues of T are computed and ordered by absolute magnitude.
  • the local orientedness o is computed as the ratio of the first and second eigenvalue. The local orientedness is shown in Fig. 5C .
  • a refined filter output is computed by (pixelwise) multiplication of the maximum linear correlation coefficient c (as shown in Fig. 5B ) with the local orientedness o (as shown in Fig. 5C ). The resulting image is depicted in Fig. 5D .
  • the line model can be more individualized, e.g. patient individual.
  • Such an individual line model can e.g. be obtained from the original image data in which dimensions of the line structure to be detected may roughly be estimated to define a useful line model.
  • any medical imaging application which requires delineation of organs or detection of interventional devices such as needles or guide wires can make use of the invention. But also in other fields the present invention can be applied for line structure detection, e.g. in material testing.
  • a computer program may be stored/distributed on a suitable non-transitory medium, such as an optical storage medium or a solid-state medium supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems.
  • a suitable non-transitory medium such as an optical storage medium or a solid-state medium supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Apparatus For Radiation Diagnosis (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)
EP13811010.1A 2012-12-03 2013-12-02 Image processing device and method Active EP2926318B1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US201261732562P 2012-12-03 2012-12-03
PCT/IB2013/060554 WO2014087313A1 (en) 2012-12-03 2013-12-02 Image processing device and method

Publications (2)

Publication Number Publication Date
EP2926318A1 EP2926318A1 (en) 2015-10-07
EP2926318B1 true EP2926318B1 (en) 2020-10-28

Family

ID=49817137

Family Applications (1)

Application Number Title Priority Date Filing Date
EP13811010.1A Active EP2926318B1 (en) 2012-12-03 2013-12-02 Image processing device and method

Country Status (7)

Country Link
US (1) US9536318B2 (pt)
EP (1) EP2926318B1 (pt)
JP (1) JP6273291B2 (pt)
CN (1) CN104838422B (pt)
BR (1) BR112015012373A2 (pt)
RU (1) RU2015126309A (pt)
WO (1) WO2014087313A1 (pt)

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9704289B2 (en) * 2014-05-06 2017-07-11 Whitecap Scientific Corporation Indexing method and system
US9675317B2 (en) * 2014-12-22 2017-06-13 Toshiba Medical Systems Corporation Interface identification apparatus and method
JP6920376B2 (ja) * 2015-07-29 2021-08-18 ペルキネルマー ヘルス サイエンシーズ， インコーポレイテッド ３ｄ解剖画像における個々の骨格の骨の自動化されたセグメンテーションのためのシステムおよび方法
JP6943866B2 (ja) * 2016-02-05 2021-10-06 プルモンクス コーポレイション 肺撮像データを分析するための方法、システム及び装置
EP3291175B1 (en) * 2016-09-05 2018-12-12 RaySearch Laboratories AB Image processing system and method for interactive contouring of three-dimensional medical data
FR3060179B1 (fr) * 2016-12-08 2020-04-03 Safran Procede et dispositif de determination des orientations d'elements de fibres dans une piece en materiau composite
WO2019000455A1 (zh) * 2017-06-30 2019-01-03 上海联影医疗科技有限公司 图像分割的方法及系统
WO2019042962A1 (en) * 2017-09-01 2019-03-07 Koninklijke Philips N.V. LOCATION OF ANATOMICAL STRUCTURES IN MEDICAL IMAGES
CN109584252B (zh) * 2017-11-03 2020-08-14 杭州依图医疗技术有限公司 基于深度学习的ct影像的肺叶段分割方法、装置
CN109697754B (zh) * 2018-12-24 2022-05-27 中国科学院大学 基于主方向估算的3d岩体点云特征面提取方法
CN111292343B (zh) * 2020-01-15 2023-04-28 东北大学 一种基于多视角下的肺叶分割方法和装置

Family Cites Families (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4930519A (en) 1984-04-02 1990-06-05 Medical Graphics Corporation Method of graphing cardiopulmonary data
JP2000222574A (ja) * 1999-01-28 2000-08-11 Hitachi Ltd ディジタル画像の線状領域抽出方法および画像処理装置
US7315639B2 (en) * 2004-03-03 2008-01-01 Mevis Gmbh Method of lung lobe segmentation and computer system
JP4544891B2 (ja) * 2004-03-30 2010-09-15 幸靖 吉永 線抽出のための画像処理方法及びそのプログラム、線集中度画像フィルタ
US7711167B2 (en) * 2005-12-07 2010-05-04 Siemens Medical Solutions Usa, Inc. Fissure detection methods for lung lobe segmentation
JP2007275346A (ja) * 2006-04-07 2007-10-25 Toshiba Corp 放射線画像処理装置、放射線画像処理方法及び放射線画像処理プログラム
WO2008035266A2 (en) 2006-09-21 2008-03-27 Koninklijke Philips Electronics N.V. Automatic seed point selection
US8144949B2 (en) 2007-11-15 2012-03-27 Carestream Health, Inc. Method for segmentation of lesions
JP5233374B2 (ja) * 2008-04-04 2013-07-10 大日本印刷株式会社 医用画像処理システム
US8150120B2 (en) 2008-05-06 2012-04-03 Carestream Health, Inc. Method for determining a bounding surface for segmentation of an anatomical object of interest
JP5051025B2 (ja) * 2008-06-26 2012-10-17 コニカミノルタホールディングス株式会社 画像生成装置、プログラム、および画像生成方法
US8724866B2 (en) * 2009-09-14 2014-05-13 Siemens Medical Solutions Usa, Inc. Multi-level contextual learning of data
US9599461B2 (en) * 2010-11-16 2017-03-21 Ectoscan Systems, Llc Surface data acquisition, storage, and assessment system
US9014445B2 (en) * 2012-10-11 2015-04-21 Vida Diagnostics, Inc. Visualization and characterization of pulmonary lobar fissures

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
None *

Also Published As

Publication number Publication date
CN104838422B (zh) 2018-06-08
RU2015126309A (ru) 2017-01-13
US20150302602A1 (en) 2015-10-22
US9536318B2 (en) 2017-01-03
JP2015536732A (ja) 2015-12-24
EP2926318A1 (en) 2015-10-07
WO2014087313A1 (en) 2014-06-12
CN104838422A (zh) 2015-08-12
BR112015012373A2 (pt) 2017-07-11
JP6273291B2 (ja) 2018-01-31

Similar Documents

Publication Publication Date Title
EP2926318B1 (en) Image processing device and method
EP2916738B1 (en) Lung, lobe, and fissure imaging systems and methods
US6909794B2 (en) Automated registration of 3-D medical scans of similar anatomical structures
US8837789B2 (en) Systems, methods, apparatuses, and computer program products for computer aided lung nodule detection in chest tomosynthesis images
US6766043B2 (en) Pleural nodule detection from CT thoracic images
US8135189B2 (en) System and method for organ segmentation using surface patch classification in 2D and 3D images
US20070223815A1 (en) Feature Weighted Medical Object Contouring Using Distance Coordinates
US20040184647A1 (en) System, method and apparatus for small pulmonary nodule computer aided diagnosis from computed tomography scans
US20110028843A1 (en) Providing a 2-dimensional ct image corresponding to a 2-dimensional ultrasound image
US7929741B2 (en) System and method for automated detection of mucus plugs within bronchial tree in MSCT images
EP2401719B1 (fr) Méthodes de segmentation d'images et de détection de structures particulières
JP2007307358A (ja) 画像処理方法および装置ならびにプログラム
Sun et al. Juxta-vascular nodule segmentation based on flow entropy and geodesic distance
US8577101B2 (en) Change assessment method
US7355605B2 (en) Method and system for automatic orientation of local visualization techniques for vessel structures
Klinder et al. Lobar fissure detection using line enhancing filters
Khaniabadi et al. Comparative review on traditional and deep learning methods for medical image segmentation
JP5632920B2 (ja) ボケイメージ内のブラーの特性を決定するシステム及び方法
US8165375B2 (en) Method and system for registering CT data sets
KR101494975B1 (ko) 3차원 자동 유방 초음파 영상의 유두 자동 검출 시스템 및 그 검출 방법
Ben-Zikri et al. A feature-based affine registration method for capturing background lung tissue deformation for ground glass nodule tracking
Jamil et al. Image registration of medical images
Ben-Zikri et al. Evaluation of a Feature-based Affine Registration Method for Lung Tissue Deformation Correction and Ground Glass Nodule Progression Assessment Medical Image Analysis
Mendonça et al. Model-Based Methods for Detection of Pulmonary Nodules
Vargas-Voracek et al. Fast search and localization algorithm based on human visual perception modeling: an application for fast localization of structures in mammograms

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

17P Request for examination filed

Effective date: 20150703

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

AX Request for extension of the european patent

Extension state: BA ME

DAX Request for extension of the european patent (deleted)
STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: EXAMINATION IS IN PROGRESS

17Q First examination report despatched

Effective date: 20180523

RAP1 Party data changed (applicant data changed or rights of an application transferred)

Owner name: KONINKLIJKE PHILIPS N.V.

Owner name: PHILIPS GMBH

REG Reference to a national code

Ref country code: DE

Ref legal event code: R079

Ref document number: 602013073647

Country of ref document: DE

Free format text: PREVIOUS MAIN CLASS: G06T0007000000

Ipc: G06T0007120000

GRAP Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOSNIGR1

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: GRANT OF PATENT IS INTENDED

RIC1 Information provided on ipc code assigned before grant

Ipc: G06T 7/12 20170101AFI20200417BHEP

INTG Intention to grant announced

Effective date: 20200507

GRAS Grant fee paid

Free format text: ORIGINAL CODE: EPIDOSNIGR3

GRAA (expected) grant

Free format text: ORIGINAL CODE: 0009210

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE PATENT HAS BEEN GRANTED

AK Designated contracting states

Kind code of ref document: B1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

REG Reference to a national code

Ref country code: GB

Ref legal event code: FG4D

REG Reference to a national code

Ref country code: CH

Ref legal event code: EP

REG Reference to a national code

Ref country code: AT

Ref legal event code: REF

Ref document number: 1328980

Country of ref document: AT

Kind code of ref document: T

Effective date: 20201115

REG Reference to a national code

Ref country code: DE

Ref legal event code: R096

Ref document number: 602013073647

Country of ref document: DE

REG Reference to a national code

Ref country code: IE

Ref legal event code: FG4D

REG Reference to a national code

Ref country code: DE

Ref legal event code: R084

Ref document number: 602013073647

Country of ref document: DE

REG Reference to a national code

Ref country code: AT

Ref legal event code: MK05

Ref document number: 1328980

Country of ref document: AT

Kind code of ref document: T

Effective date: 20201028

REG Reference to a national code

Ref country code: NL

Ref legal event code: MP

Effective date: 20201028

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: RS

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20201028

Ref country code: FI

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20201028

Ref country code: NO

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20210128

Ref country code: PT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20210301

Ref country code: NL

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20201028

Ref country code: GR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20210129

REG Reference to a national code

Ref country code: LT

Ref legal event code: MG4D

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: LV

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20201028

Ref country code: IS

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20210228

Ref country code: SE

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20201028

Ref country code: PL

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20201028

Ref country code: ES

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20201028

Ref country code: AT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20201028

Ref country code: BG

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20210128

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: HR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20201028

REG Reference to a national code

Ref country code: DE

Ref legal event code: R097

Ref document number: 602013073647

Country of ref document: DE

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: LT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20201028

Ref country code: RO

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20201028

Ref country code: SK

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20201028

Ref country code: SM

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20201028

Ref country code: EE

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20201028

Ref country code: CZ

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20201028

REG Reference to a national code

Ref country code: CH

Ref legal event code: PL

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: DK

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20201028

Ref country code: MC

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20201028

PLBE No opposition filed within time limit

Free format text: ORIGINAL CODE: 0009261

REG Reference to a national code

Ref country code: BE

Ref legal event code: MM

Effective date: 20201231

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT

GBPC Gb: european patent ceased through non-payment of renewal fee

Effective date: 20210128

26N No opposition filed

Effective date: 20210729

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: IE

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20201202

Ref country code: IT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20201028

Ref country code: LU

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20201202

Ref country code: FR

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20201228

Ref country code: AL

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20201028

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: SI

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20201028

Ref country code: GB

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20210128

Ref country code: CH

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20201231

Ref country code: LI

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20201231

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: IS

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20210228

Ref country code: TR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20201028

Ref country code: MT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20201028

Ref country code: CY

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20201028

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: MK

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20201028

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: BE

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20201231

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: DE

Payment date: 20231227

Year of fee payment: 11